© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 54049
    Prev
    Next
    INDEX
    Explanations

    cabinet positions or office

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    strap
    -0.10
    amel
    -0.10
    ed
    -0.09
    entication
    -0.09
    stairs
    -0.09
    enson
    -0.09
    itecture
    -0.08
    board
    -0.08
    uras
    -0.08
    ©
    -0.08
    POSITIVE LOGITS
    atel
    0.11
    lv
    0.09
    nda
    0.08
    aces
    0.08
     Dund
    0.08
    oor
    0.08
    rtle
    0.08
    atro
    0.08
     organs
    0.08
    onet
    0.08
    Activations Density 0.002%

    No Known Activations